[Push] Provided Examples

[Raphael Crawford-Marks]

Stefan,

Sometimes a GP run won't find a solution...it gets stuck in some local
minima from which it can't escape.  This goes for all GP, not just PushGP.
Try setting the generation limit in PushGP (*max-generations*, I think) to
something smaller, like 50 or 100.  Then do several runs.  The default
problem is a pretty easy one, so it should find a solution most of the time.
Also, your machine speed has nothing to do with the problem-solving ability
of the GP system....just how fast it goes.

Good luck,

Raphael


>
Hi there!

I'm quite new to the subject of Genetic Programming. The work done with Push
seems very appealing to me. Would you help me getting started?

I downloaded the accompanying LISP code yesterday and tried the default
problem by simply loading the file named "load". Suprisingly, there wasn't a
solution after 1000 generations.

Is that problem really so hard ... or our machine so slow?

Thanks a lot for all your effort.

Stefan Mandl


_______________________________________________
Push mailing list
Push at lists.hampshire.edu
http://lists.hampshire.edu/mailman/listinfo/push